Improved Transferability of Data‐Driven Damage Models Through Sample Selection Bias Correction

Damage models for natural hazards are used for decision making on reducing and transferring risk. The damage estimates from these models depend on many variables and their complex sometimes nonlinear relationships with the damage. In recent years, data‐driven modeling techniques have been used to capture those relationships. The available data to build such models are often limited. Therefore, in practice it is usually necessary to transfer models to a different context. In this article, we show that this implies the samples used to build the model are often not fully representative for the situation where they need to be applied on, which leads to a “sample selection bias.” In this article, we enhance data‐driven damage models by applying methods, not previously applied to damage modeling, to correct for this bias before the machine learning (ML) models are trained. We demonstrate this with case studies on flooding in Europe, and typhoon wind damage in the Philippines. Two sample selection bias correction methods from the ML literature are applied and one of these methods is also adjusted to our problem. These three methods are combined with stochastic generation of synthetic damage data. We demonstrate that for both case studies, the sample selection bias correction techniques reduce model errors, especially for the mean bias error this reduction can be larger than 30%. The novel combination with stochastic data generation seems to enhance these techniques. This shows that sample selection bias correction methods are beneficial for damage model transfer.     

Age Is But a Number? An Exploration of Age Differences in Episodic Volunteering

VOLUNTAS: International Journal of Voluntary and Nonprofit Organizations - Age has long been understood as a strong demographic determinant of volunteering. However, to date, limited literature...     

Has Opposition to Immigration Increased in the United States after the Economic Crisis? An Experimental Approach

We employ two population‐level experiments to accurately measure opposition to immigration before and after the economic crisis of 2008. Our design explicitly addresses social desirability bias, which is the tendency to give responses that are seen favorably by others and can lead to substantial underreporting of opposition to immigration. We find that overt opposition to immigration, expressed as support for a closed border, increases slightly after the crisis. However, once we account for social desirability bias, no significant increase remains. We conclude that the observed increase in anti‐immigration sentiment in the post‐crisis United States is attributable to greater expression of opposition rather than any underlying change in attitudes.     

‘Rachel's not here’: Constructed dialogue in gossip

Sociolinguistic research has demonstrated that gossip is a co‐constructed phenomenon, which allows participants to establish solidarity and build alignments with each other, while evaluating an absent party. Gossip can also serve important social functions, such as helping to establish and reconfirm group norms and values. The present study provides a detailed analysis of an extended gossip episode that occurred within an institutional context: a study group interaction at a U.S. university. Our analysis shows how, in gossip, constructed dialogue both prompts and legitimizes pejorative evaluations towards an absent third party, and is actually the pivot around which group members negotiate values and norms in the process of arriving at a shared moral stance. Our analysis also demonstrates that alignment in gossip interactions is tenuous and must be continuously renewed.     

A new long-term survival model with dispersion induced by discrete frailty

Lifetime Data Analysis - Frailty models are generally used to model heterogeneity between the individuals. The distribution of the frailty variable is often assumed to be continuous. However, there...     

Inference and Decision Making for 21st-Century Drug Development and Approval

ABSTRACT

The cost and time of pharmaceutical drug development continue to grow at rates that many say are unsustainable. These trends have enormous impact on what treatments get to patients, when they get them and how they are used. The statistical framework for supporting decisions in regulated clinical development of new medicines has followed a traditional path of frequentist methodology. Trials using hypothesis tests of “no treatment effect” are done routinely, and the p-value < 0.05 is often the determinant of what constitutes a “successful” trial. Many drugs fail in clinical development, adding to the cost of new medicines, and some evidence points blame at the deficiencies of the frequentist paradigm. An unknown number effective medicines may have been abandoned because trials were declared “unsuccessful” due to a p-value exceeding 0.05. Recently, the Bayesian paradigm has shown utility in the clinical drug development process for its probability-based inference. We argue for a Bayesian approach that employs data from other trials as a “prior” for Phase 3 trials so that synthesized evidence across trials can be utilized to compute probability statements that are valuable for understanding the magnitude of treatment effect. Such a Bayesian paradigm provides a promising framework for improving statistical inference and regulatory decision making.